This decommissioned ERA site remains active temporarily to support our final migration steps to https://ualberta.scholaris.ca, ERA's new home. All new collections and items, including Spring 2025 theses, are at that site. For assistance, please contact erahelp@ualberta.ca.
- 364 views
- 571 downloads
Automatic Brain Tumor Segmentation
-
- Author(s) / Creator(s)
-
Technical report TR05-13. This thesis addresses the task of automatic segmentation of brain tumors and edema in Magnetic Resonance images. This is motivated by potential applications in assessing tumor growth, assessing treatment responses, computer-assisted surgery, radiation therapy target planning, and the construction of tumor growth models. The presented framework forms an image processing pipeline, consisting of noise reduction, spatial registration, intensity standardization, feature extraction, pixel classification, and label relaxation. The key advantage of this framework is the simultaneous use of features computed from the image intensity properties, and the locations of pixels within an aligned template brain in a standard coordinate system. Automatically learning to combine these features allows recognition of tumors and edema that have relatively normal intensity properties. Our results on 11 patients with brain tumors show that the system achieves nearly perfect performance given patient-specific training, but also achieves accurate results in segmenting patients not used in training. | TRID-ID TR05-13
-
- Date created
- 2005
-
- Subjects / Keywords
-
- Type of Item
- Report
-
- License
- Attribution 3.0 International